Data Poisoning against Differentially-Private Learners: Attacks and Defenses

03/23/2019
by   Yuzhe Ma, et al.
0

Data poisoning attacks aim to manipulate the model produced by a learning algorithm by adversarially modifying the training set. We consider differential privacy as a defensive measure against this type of attack. We show that such learners are resistant to data poisoning attacks when the adversary is only able to poison a small number of items. However, this protection degrades as the adversary poisons more data. To illustrate, we design attack algorithms targeting objective and output perturbation learners, two standard approaches to differentially-private machine learning. Experiments show that our methods are effective when the attacker is allowed to poison sufficiently many training items.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/07/2018

Three Tools for Practical Differential Privacy

Differentially private learning on real-world data poses challenges for ...
research
03/05/2019

Online Data Poisoning Attack

We study data poisoning attacks in the online learning setting where the...
research
05/13/2019

Differentially Private Empirical Risk Minimization with Sparsity-Inducing Norms

Differential privacy is concerned about the prediction quality while mea...
research
05/12/2021

A Statistical Threshold for Adversarial Classification in Laplace Mechanisms

This paper studies the statistical characterization of detecting an adve...
research
11/18/2020

Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff

Data poisoning and backdoor attacks manipulate victim models by maliciou...
research
10/25/2022

Robustness of Locally Differentially Private Graph Analysis Against Poisoning

Locally differentially private (LDP) graph analysis allows private analy...
research
07/27/2020

Privacy-Preserving Resilience of Cyber-Physical Systems to Adversaries

A cyber-physical system (CPS) is expected to be resilient to more than o...

Please sign up or login with your details

Forgot password? Click here to reset